© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21453
    Prev
    Next
    INDEX
    Explanations

    positive evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĨ
    -0.10
    isu
    -0.10
    åĪ¹
    -0.09
    æ¯ıæ¯ı
    -0.09
    æĸ°è¥¿
    -0.09
    æµ®çİ°
    -0.09
    afs
    -0.09
    åĪ»èĭ¦
    -0.09
    æģ¯æģ¯
    -0.09
    åĽłä¸ºæĪij们
    -0.09
    POSITIVE LOGITS
    羣çļĦ
    0.10
    å¾Īå¥½åľ°
    0.09
    ä¸İåħ¶ä»ĸ
    0.09
     really
    0.09
    åľ¨æĪij
    0.09
    åģļå·¥
    0.08
    ä¹Łå¾Ī
    0.08
    å¾Ī好çļĦ
    0.08
    羣çļĦå¾Ī
    0.08
    对æĪij
    0.08
    Activations Density 0.045%

    No Known Activations